Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 349 896 972 144 942 136 773 292 540 258 831 449 362 207 262 952 312 261 546  28
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 258 540  NA 449 831 136 207 773 292 952 362 349 261  28 312 262 896  NA  NA 546 942 144 972
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 2 4 5 3 2 3 2 5 5 1
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "j" "u" "q" "y" "b" "I" "L" "D" "Q" "X"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  3  5 16
which( manyNumbersWithNA > 900 )
[1] 10 21 23
which( is.na( manyNumbersWithNA ) )
[1]  3 18 19

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 972 942 952
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 972 942 952
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 972 942 952

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "I" "L" "D" "Q" "X"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "j" "u" "q" "y" "b"
manyNumbers %in% 300:600
 [1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE
which( manyNumbers %in% 300:600 )
[1]  1  9 12 13 17 19
sum( manyNumbers %in% 300:600 )
[1] 6

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "large" NA      "small" "large" "small" "small" "large" "small" "large" "small" "small" "small" "small" "small" "small"
[17] "large" NA      NA      "large" "large" "small" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "large"   "UNKNOWN" "small"   "large"   "small"   "small"   "large"   "small"   "large"   "small"   "small"   "small"  
[14] "small"   "small"   "small"   "large"   "UNKNOWN" "UNKNOWN" "large"   "large"   "small"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0 540  NA   0 831   0   0 773   0 952   0   0   0   0   0   0 896  NA  NA 546 942   0 972

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 2 4 5 3 1
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  2  4  5  3  1
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 23
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 972
which.min( manyNumbersWithNA )
[1] 14
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 28
range( manyNumbersWithNA, na.rm = TRUE )
[1]  28 972

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 258 540  NA 449 831 136 207 773 292 952 362 349 261  28 312 262 896  NA  NA 546 942 144 972
sort( manyNumbersWithNA )
 [1]  28 136 144 207 258 261 262 292 312 349 362 449 540 546 773 831 896 942 952 972
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  28 136 144 207 258 261 262 292 312 349 362 449 540 546 773 831 896 942 952 972  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 972 952 942 896 831 773 546 540 449 362 349 312 292 262 261 258 207 144 136  28  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 258 540  NA 449 831
order( manyNumbersWithNA[1:5] )
[1] 1 4 2 5 3
rank( manyNumbersWithNA[1:5] )
[1] 1 3 5 2 4
sort( mixedLetters )
 [1] "b" "D" "I" "j" "L" "q" "Q" "u" "X" "y"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 1.5 6.5 1.5 3.5 9.5 9.5 3.5 6.5 6.5 6.5
rank( manyDuplicates, ties.method = "min" )
 [1] 1 5 1 3 9 9 3 5 5 5
rank( manyDuplicates, ties.method = "random" )
 [1]  1  8  2  3 10  9  4  5  6  7

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000  1.36859221 -0.38183541 -0.30943528 -0.03977668  0.86543151
[11]  1.25225319  1.12200614  1.55306833  0.90868448 -1.46379116
round( v, 0 )
 [1] -1  0  0  0  1  1  0  0  0  1  1  1  2  1 -1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  1.4 -0.4 -0.3  0.0  0.9  1.3  1.1  1.6  0.9 -1.5
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  1.37 -0.38 -0.31 -0.04  0.87  1.25  1.12  1.55  0.91 -1.46
floor( v )
 [1] -1 -1  0  0  1  1 -1 -1 -1  0  1  1  1  0 -2
ceiling( v )
 [1] -1  0  0  1  1  2  0  0  0  1  2  2  2  1 -1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC